Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verdict
    -0.07
     mitigate
    -0.06
    Mayor
    -0.06
    :
↵
↵
    -0.06
     Degree
    -0.06
    .tabPage
    -0.06
    kın
    -0.06
     composers
    -0.06
     khiển
    -0.06
     quake
    -0.06
    POSITIVE LOGITS
    -sidebar
    0.07
    aleigh
    0.06
    ÜRK
    0.06
    ()%
    0.06
    VersionUID
    0.06
     buggy
    0.06
    isco
    0.06
    abee
    0.06
    -title
    0.06
    _water
    0.06
    Act Density 0.201%

    No Known Activations